Upload 8 files

.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Because notebook is only for testing
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 karuniaperjuangan
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,13 +1 @@
----
-title: Bangkit Chatbot
-emoji: 🏢
-colorFrom: gray
-colorTo: purple
-sdk: gradio
-sdk_version: 3.42.0
-app_file: app.py
-pinned: false
-license: cc-by-3.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Chatbot Konseling Masalah Kekerasan Seksual

app.py

@@ -0,0 +1,62 @@
+"""
+Ini adalah kode utama untuk menjalankan aplikasi chatbot
+"""
+
+from dotenv import load_dotenv
+
+load_dotenv()  # take environment variables from .env.
+
+import os
+
+from langchain.chat_models import ChatOpenAI
+from langchain.prompts.chat import (
+    ChatPromptTemplate,
+    SystemMessagePromptTemplate,
+    AIMessagePromptTemplate,
+    HumanMessagePromptTemplate,
+)
+import faiss
+from langchain.chat_models import ChatOpenAI
+from langchain.chains import RetrievalQAWithSourcesChain
+import pickle
+from langchain.vectorstores import FAISS
+from typing import List
+import gradio as gr
+from langchain.schema import AIMessage, HumanMessage, SystemMessage
+
+chat = ChatOpenAI(temperature=0)
+
+# Load the LangChain.
+index = faiss.read_index("docs.index")
+
+with open("faiss_store.pkl", "rb") as f:
+    store:FAISS = pickle.load(f)
+
+store.index = index
+
+def ask_retrieval_qa(question:str,history:List[List[str]]):
+    answers = store.similarity_search("Apa kontak yang bisa dihubungi untuk menghadapi kasus kekerasan seksual?", k=1)
+    messages = [
+        SystemMessage(content=f"""Kamu adalah sebuah chatbot yang bernama Bangkit. Tugasmu adalah membantu orang-orang yang mengalami masalah kekerasan seksual. Kamu akan memberikan informasi yang dapat membantu seseorang untuk melakukan tindak lanjut terhadap kasus kekerasan seksual yang dialami.
+Anda bisa menggunakan potongan UU No 12 tahun 2022 berikut untuk membantu Anda:
+{answers[0].page_content}
+Sumber: {answers[0].metadata}"""),
+        
+    ]
+    for human,ai in history:
+        messages.append(HumanMessage(content=human))
+        messages.append(AIMessage(content=ai))
+    messages.append(HumanMessage(content=question))
+    response = chat(messages)
+    return response.content
+
+with gr.Blocks() as demo:
+    
+    gr.Markdown("""<h1 style="text-align:center">Aplikasi Bangkit (Intelligent Chatbot for Sexual Violence Behaviour) </h1>""")
+    gr.Markdown(
+        """
+        Gunakan chatbot di bawah untuk menangani kasus kekerasan seksual yang anda alami.
+        """        )
+    gr.ChatInterface(ask_retrieval_qa)
+demo.launch(auth=(os.environ.get("GRADIO_USERNAME"),os.environ.get("GRADIO_PASSWORD")))
+

extract_pdf.py

@@ -0,0 +1,49 @@
+"""
+Kode di bawah digunakan untuk mengextract teks dari file pdf yang ada di folder document
+"""
+from pathlib import Path
+from langchain.text_splitter import CharacterTextSplitter
+import faiss
+from langchain.vectorstores import FAISS
+from langchain.embeddings import OpenAIEmbeddings
+import pickle
+import re
+
+from langchain.document_loaders import PyPDFLoader
+
+paths = Path("document/").glob("**/*.pdf")
+docs = []
+for path in paths:
+    path = str(path)
+    loader = PyPDFLoader(path)
+    pages = loader.load_and_split()
+    pages
+    document = []
+    for page in pages:
+        content = page.page_content
+        #Kode di bawah untuk menghilangkan header dan footer
+        content = re.sub(r"PRES(.*)\n(.*)\n-.*-\n", " ", content)
+        content = re.sub(r"FRES(.*)\n(.*)\n-.*-\n", " ", content)
+        content = re.sub(r"PRESIDEN\nREPUBLIK INDONESIA\n.11-\n", " ", content)
+        content = re.sub(r"PRESIDEN\nREPUBLIK INOONESIA\n_55_\n", " ", content)
+        content = re.sub(r"PRESIDEN\nREPUBLIK INDONESIA\n.20 -\n", " ", content)
+        content = re.sub(r"PRESIDEN\nREPUBLIK INDONESIA\n24-", " ", content)
+        content = re.sub(r"PRESIOEN\nREPUBLIK INDONESIA\n-39\n", " ", content)
+        content = re.sub(r"PRESIDEN\nREPUELIK INDONESIA\nL2-\n", " ", content)
+        document.append({"content": content,"metadata":{'source':page.metadata['source']}})
+    document
+
+    #join content every 3 pages
+
+    for i in range(0, len(pages), 3):
+        docs.append({'content':" ".join([page['content'] for page in document][i:i+3]),
+                    'metadata':{'source':document[i]['metadata']['source']}
+                    })
+
+# Here we create a vector store from the documents and save it to disk.
+list_content = [doc['content'] for doc in docs]
+list_metadata = [doc['metadata'] for doc in docs]
+store = FAISS.from_texts(list_content, OpenAIEmbeddings(), metadatas=list_metadata)
+faiss.write_index(store.index, "docs.index")
+store.index = None
+

faiss_store.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1bad3bcd607c13b2d45bb5c618519000a4367004be45ac237eb700fbf77cb9a
+size 90972

requirements.txt

@@ -0,0 +1,7 @@
+langchain
+openai
+faiss-cpu
+gradio
+tiktoken
+python-dotenv
+pypdf